提出可逆机器学习模型遗忘方法，实现对特定数据的可控删除。
How to unlearn a learned Machine Learning model ?
- 设计一种优雅算法，从训练数据中移除特定样本影响
- 构建数学理论支撑，量化模型对被遗忘数据的无知程度
- 适用于需合规删除用户数据的AI系统开发
当前机器学习在多个领域引发革命性进展，但其输出与能力的监管日益重要。一种可行方案是通过控制训练数据来实现模型的遗忘，即从模型中移除特定数据的影响。本文提出一种优雅的遗忘算法并进行可视化演示，阐明其背后的数学理论，建立评估指标：一为模型在保留数据上的性能表现，二为模型对被遗忘数据的无知程度。该框架支持对模型记忆的精确控制，为满足数据合规性要求提供技术路径。
原文摘要 · Abstract (English)
In contemporary times, machine learning (ML) has sparked a remarkable revolution across numerous domains, surpassing even the loftiest of human expectations. However, despite the astounding progress made by ML, the need to regulate its outputs and capabilities has become imperative. A viable approach to address this concern is by exerting control over the data used for its training, more precisely, by unlearning the model from undesired data. In this article, I will present an elegant algorithm for unlearning a machine learning model and visualize its abilities. Additionally, I will elucidate the underlying mathematical theory and establish specific metrics to evaluate both the unlearned model's performance on desired data and its level of ignorance regarding unwanted data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。